Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 24
Encontrada(s) 1 página(s)

RIUMA. Repositorio Institucional de la Universidad de Málaga
Publication Contribución de congreso (ConferenceOutput)

Category Theory Framework for Variability Models with Non-Functional Requirements.

  • Muñoz-Guerra, Daniel Jesús
  • Gurov, Dilian
  • Pinto-Alarcón, Mónica
  • Fuentes-Fernández, Lidia
Munoz, Pinto and Fuentes work is supported by the European Union's H2020 research and innovation programme under grant agreement DAEMON 101017109, by the projects co-financed by FEDER funds LEIA UMA18-FEDERJA-15, MEDEA RTI2018-099213-B-I00 and Rhea P18-FR-1081 and the PRE2019-087496 grant from the Ministerio de Ciencia e Innovación., https://www.springernature.com/gp/open-science/policies/book-policies, In Software Product Line (SPL) engineering one uses Variability Models (VMs) as input to automated reasoners to generate optimal products according to certain Quality Attributes (QAs). Variability models, however, and more specifically those including numerical features (i.e., NVMs), do not natively support QAs, and consequently, neither do automated reasoners commonly used for variability resolution. However, those satisfiability and optimisation problems have been covered and refined in other relational models such as databases. Category Theory (CT) is an abstract mathematical theory typically used to capture the common aspects of seemingly dissimilar algebraic structures. We propose a unified relational modelling framework subsuming the structured objects of VMs and QAs and their relationships into algebraic categories. This abstraction allows a combination of automated reasoners over different domains to analyse SPLs. The solutions’ optimisation can now be natively performed by a combination of automated theorem proving, hashing, balanced-trees and chasing algorithms. We validate this approach by means of the edge computing SPL tool HADAS.
RIUMA. Repositorio Institucional de la Universidad de Málaga
Publication Contribución de congreso (ConferenceOutput)

Quality-aware analysis and optimisation of virtual network functions.

  • Muñoz-Guerra, Daniel Jesús
  • Pinto-Alarcón, Mónica
  • Fuentes-Fernández, Lidia
This work is supported by the European Union’s H2020 research and innovation programme under grant agreementDAEMON101017109, by the projects co-financed by FEDER funds LEIA UMA18-FEDERJA- 15, MEDEA RTI2018-099213-B-I00 and Rhea P18-FR-1081 and the PRE2019-087496 grant from the Ministerio de Ciencia e Innovación., https://authors.acm.org/author-resources/author-rights, The softwarisation and virtualisation of network functionality is the last milestone in the networking industry. Software-Defined Networks (SDN) and Network Function Virtualization (NFV) offer the possibility of using software to manage computer and mobile networks and build novel Virtual Network Functions (VNFs) deployed in heterogeneous devices. To reason about the variability of network functions and especially about the quality of a software product defined as a set of VNFs instantiated as part of a service (i.e., Service Function Chaining), a variability model along with a quality model is required. However, this domain imposes certain challenges to quality-aware reasoning of service function chains, such as numerical features or configuration-level Quality Attributes (QAs) (e.g., energy consumption). Incorporating numerical reasoning with quality data into SPL analyses is challenging and tool support is rare. In this work, we present 3 groups of operations: model report, aggregate functions to dynamically convert QAs at the feature-level into the configuration-level, and quality-aware optimisation. Our objective is to test the most complete reasoning tools to exploit the extended variability with quality attributes needed for VNFs.
RIUMA. Repositorio Institucional de la Universidad de Málaga
Publication Contribución de congreso (ConferenceOutput)

Nemo: A Tool to Transform Feature Models with Numerical Features and Arithmetic Constraints.

  • Muñoz-Guerra, Daniel Jesús
  • Oh, Jeho
  • Pinto-Alarcón, Mónica
  • Fuentes-Fernández, Lidia
  • Batory, Don
Munoz, Pinto and Fuentes work is supported by the European Union’s H2020 research and innovation programme under grant agreement DAEMON 101017109, by the projects co-financed by FEDER funds LEIA UMA18-FEDERJA-15, MEDEA RTI2018-099213-B-I00 and Rhea P18-FR-1081 and the PRE2019-087496 grant from the Ministerio de Ciencia e Innovación. Batory is retired, writing free textbooks [5], and is walking dogs for wages., https://www.springernature.com/gp/open-science/policies/book-policies, Real-world Software Product Lines (SPLs) need Numerical Feature Models (NFMs) whose features not only have boolean values satisfying boolean constraints, but also have numeric attributes satisfying arithmetic constraints. A key operation on NFMs finds near-optimal performing products, which requires counting the number of SPL products. Typical constraint satisfaction solvers perform poorly on counting. Nemo (Numbers, features, models) supports NFMs by bit-blasting, the technique that encodes arithmetic as boolean clauses. Nemo translates NFMs to propositional formulas whose products can be counted efficiently by #SAT solvers, enabling near-optimal products to be found. We evaluate Nemo with a diverse set of real-world NFMs, complex arithmetic constraints, and counting experiments in this paper.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices

  • Alcalá Marín, Sergi
  • Bazco-Nogueras, Antonio
  • Banchs Roca, Albert
  • Fiore, Marco
Cloud-native mobile networks pave the road for Network Slicing as a Service (NSaaS), where slice overbooking is a promising management strategy to maximize the revenues from admitted slices by exploiting the fact they are unlikely to fully utilize their reserved resources concurrently. While seminal works have shown the potential of overbooking for NSaaS in simplistic cases, its realization is challenging in practical scenarios with realistic slice demands, where its actual performance remains to be tested. In this paper, we propose kaNSaaS, a complete solution for NSaaS management with slice overbooking that combines deep learning and classical optimization to jointly solve the key tasks of admission control and resource allocation. Experiments with large-scale measurement data of actual tenant demands show that kaNSaaS increases the network operator profits by 300% with respect to NSaaS management strategies that do not employ overbooking, while outperforming by more than 20% state-of-the-art overbooking-based approaches., We thank the Mobihoc anonymous reviewers for their helpful comments and guidance. The work of S. Alcalá-Marín was supported by the European Union's Horizon 2020 research and innovation programme under grant agreements no. 101017109 "DAEMON". The work of A. Bazco-Nogueras was supported by the Regional Government of Madrid through the grant 2020-T2/TIC-20710 for Talent Attraction. The work of A. Banchs was also supported in part by the European Union's Horizon-JU-SNS-2022 Research and Innovation Programme under Grant Agreement No. 101095871 (TrialsNet) and by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGeneration EU through the UNICO 5G I+D 6G-CLARION project. The work of M. Fiore was supported by the European Union-NextGenerationEU through the UNICO 5G I+D project no. TSI-063000-2021-52 "AEON-ZERO".
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Requirements and Specifications for the Orchestration of Network Intelligence in 6G

  • Camelo, Miguel
  • Cominardi, Luca
  • Gramaglia, Marco
  • Fiore, Marco
  • García Saavedra, Andrés
  • Fuentes, Lidia
  • Soto, Paola
  • Slamnik-Kriještorac, Nina
  • Ballesteros, Joaquín
  • Chang, Chia-Yu
  • Baldoni, Gabriele
  • Márquez-Barja, Johann M.
  • Hellinckx, Peter
  • Latré, Steven
Next-generation mobile networks are expected to flaunt highly (if not fully) automated management. Network Intelligence (NI) will be the key enabler for such a vision, empowering myriad of orchestrators and controllers across network domains. In this paper, we elaborate on the DAEMON architectural model, which proposes introducing a NI Orchestration layer for the effective end-to-end coordination of NI instances deployed across the whole mobile network infrastructure. Specifically, we first outline requirements and specifications for NI design that stem from data management, control timescales, and network technology characteristics. Then, we build on such analysis to derive initial principles for the design of the NI Orchestration layer, focusing on (i) proposals for the interaction loop between NI instances and the NI Orchestrator, and (ii) a unified representation of NI algorithms based on an extended MAPE-K model. Our work contributes to the definition of the interfaces and operation of a NI Orchestration layer that foster a native integration of NI in mobile network architectures., This project has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement no.101017109 DAEMON.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Orchestration Procedures for the Network Intelligence Stratum in 6G Networks

  • Chatzieleftheriou, Livia Elena
  • Gramaglia, Marco
  • Camelo, Miguel
  • García-Saavedra, Andrés
  • Kosmatos, Evangelos
  • Gucciardo, Michele
  • Soto, Paola
  • Iosifidis, George
  • Fuentes, Lidia
  • García Avilés, Ginés
  • Lutu, Andra Elena
  • Baldoni, Gabriele
  • Fiore, Marco
Proceeding of: 2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), 6-9 June 2023, Gothenburg, Sweden. pp.: 347-352., The quest for autonomous mobile networks introduces the need for fully native support for Network Intelligence (NI) algorithms, typically based on Artificial Intelligence tools like Machine Learning, which shall be gathered into a NI stratum. The NI stratum is responsible for the full automation of the NI operation in the network, including the management of the life-cycle of NI algorithms, in a way that is synergic with traditional network management and orchestration framework. In this regard, the NI stratum must accommodate the unique requirements of NI algorithms, which differ from the ones of, e.g., virtual network functions, and thus plays a critical role in the native integration of NI into current network architectures. In this paper, we leverage the recently proposed concept of Network Intelligence Orchestrator (NIO) to (i) define the specific requirements of NI algorithms, and (ii) discuss the procedures that shall be supported by an NIO sitting in the NI stratum to effectively manage NI algorithms. We then (iii) introduce a reference implementation of the NIO defined above using cloud-native open-source tools., This work has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”., Publicado
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Demo: Nuberu - A Reliable DU DesignSuitable for Virtualization Platforms

  • García Avilés, Ginés
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Costa-Pérez, Xavier
  • Serrano Yáñez-Mingot, Pablo
  • Banchs Roca, Albert
We demonstrate Nuberu. The scenario consists of a DU under test (DuT), and one or more DUs sharing computing resources. A dashboard lets us control the type of DuT: Baseline, implemented with vanilla srsRAN, or Nuberu; the number of competing vDUs; and their SNR. A second screen shows real-time metrics: the processing latency of the TBs from each vDU instance; the throughput performance of DuT; the processing latency of DU jobs from DuT; and the ratio of latency constraint violations of DuT jobs. We show how the throughput attained by the baseline DU approach collapses upon sufficiently high computing interference from the competing DUs. Conversely, we show that the DU design introduced in [3] preserves reliability irrespective of the computing interference., This work has been supported by the EC through Grant No. 101017109 (DAEMON) and Grant No. 856709 (5Growth).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

DAEMON: A network intelligence plane for 6G networks

  • Camelo, Miguel
  • Gramaglia, Marco
  • Soto, Paola
  • Fuentes, Lidia
  • Ballesteros, Joaquín
  • Bazco-Nogueras, Antonio
  • García Avilés, Ginés
  • Latré, Steven
  • García Saavedra, Andrés
  • Fiore, Marco
Proceedings of: IEEE Global Communications Conference, 04-08 December 2022, Rio de Janeiro, Brazil., While there is a clear trend towards network automation through the usage of Artificial Intelligence (AI) and Machine Learning (ML) solutions, the major reference network architectures are still not natively including all the mechanisms needed to handle Network Intelligence (NI). This paper introduces a novel architecture proposed within the EU-funded DAEMON project, which includes a Network Intelligence Plane (NIP) that natively integrates NI into the network operation, management, and orchestration procedures. We do so by analyzing the gaps in current reference architectures and designing a Network Intelligence Orchestration (NIO) that handles the most important NI-related mechanisms such as lifecycle management, coordination, and data management., This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement no.101017109 "DAEMON".
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Network intelligence in 6G: challenges and opportunities

  • Banchs Roca, Albert
  • Fiore, Marco
  • García Saavedra, Andrés
  • Gramaglia, Marco
Proceeding of: the 16th ACM Workshop on Mobility in the Evolving Internet Architecture (in conjunction with MobiCom 2021: The 27th Annual International Conference On Mobile Computing And Networking, January 31-February 04, 2022, New Orleans, United States), The success of the upcoming 6G systems will largely depend on the quality of the Network Intelligence (NI) that will fully automate network management. Artificial Intelligence (AI) models are commonly regarded as the cornerstone for NI design, as they have proven extremely successful at solving hard problems that require inferring complex relationships from entangled, massive (network traffic) data. However, the common approach of plugging "vanilla" AI models into controllers and orchestrators does not fulfil the potential of the technology. Instead, AI models should be tailored to the specific network level and respond to the specific needs of network functions, eventually coordinated by an end-to-end NI-native architecture for 6G. In this paper, we discuss these challenges and provide results for a candidate NI-driven functionality that is properly integrated into the proposed architecture: network capacity forecasting., The authors of this paper have received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101017109 (DAEMON Network intelligence for aDAptive and sElf-Learning MObile Networks). This paper is also funded by the Spanish State Research Agency (TRUE5G project, PID2019-108713RB-C52PID2019-108713RB-C52 /AEI / 10.13039/501100011033), Publicado
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Network Intelligence for Virtualized RAN Orchestration: The DAEMON Approach

  • Gramaglia, Marco
  • Camelo, Miguel
  • Fuentes, Lidia
  • Ballesteros, Joaquín
  • Baldoni, Gabriele
  • Cominardi, Luca
  • García Saavedra, Andrés
  • Fiore, Marco
Next-generation mobile networks will largely benefit from advances in softwarization and cloudification of network functions. However, fully exploiting the new potential of flexible network architectures in front of increasingly demanding service volumes and requirements calls for an extremely effective integration of Network Intelligence (NI) solutions into production infrastructures.While current standardization efforts towards embedding NI in beyond-5G and 6G systems are still in their infancy, the DAEMON project is developing technologies for a NI-native generation of mobile networks.In this paper, we present current evolutions proposed by DAEMON in terms of a general model for the representation of NI instances, which facilitates their synergic integration in network environments. We showcase the practical viability and advantages of the proposed approach with two state-of-the-art NI algorithms for vRAN orchestration implemented into an open-source data flow programming framework., This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement no.101017109 DAEMON
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Forecasting for Network Management with Joint Statistical Modelling and Machine Learning

  • Lo Schiavo, Leonardo
  • Fiore, Marco
  • Gramaglia, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
Forecasting is a task of ever increasing importance for the operation of mobile networks, where it supports anticipa tory decisions by network intelligence and enables emerging zero touch service and network management models. While current trends in forecasting for anticipatory networking lean towards the systematic adoption of models that are purely based on deep learning approaches, we pave the way for a different strategy to the design of predictors for mobile network environments. Specifically, following recent advances in time series prediction, we consider a hybrid approach that blends statistical modelling and machine learning by means of a joint training process of the two methods. By tailoring this mixed forecasting engine to the specific requirements of network traffic demands, we develop a Thresholded Exponential Smoothing and Recurrent Neural Network (TES-RNN) model. We experiment with TES RNN in two practical network management use cases, i.e., (i) anticipatory allocation of network resources, and (ii) mobile traffic anomaly prediction. Results obtained with extensive traffic workloads collected in an operational mobile network show that TES-RNN can yield substantial performance gains over current state-of-the-art predictors in both applications considered, This work is partially supported by the European Union's Horizon 2020 research and innovation programme under grant agreement no.101017109 DAEMON. This work is partially supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D 6GCLARION-OR and AEON-ZERO. The authors would like to thank Dario Bega for his contribution to developing the forecasting use case I, and Slawek Smyl for his feedback on the baseline ES-RNN model.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Network Intelligence in Action: the DAEMON Perspective

  • Chatzieleftheriou, Livia Elena
  • Gramaglia, Marco
  • Fiore, Marco
  • Slamnik-Kriještorac, Nina
  • Camelo, Miguel
  • Soto, Paola
  • Kosmatos, Evangelos
  • García Saavedra, Andrés
  • Gucciardo, Michele
Proceedings of 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6g Summit), 3-6 Jun. 2024, Antwerp, Belgium, The native integration of AI and ML algorithms in the next-generation mobile network architecture will allow for meeting the expectations of 6G. This aspect is targeted by the DAEMON project, which proposed a solution to natively manage Network Intelligence (NI) through novel architectural elements and procedures. In this paper, we discuss how NI solutions based on AI and ML can leverage NI native procedures implemented by the NI Orchestrator to improve their lifecycle management. We also discuss how the architectural procedures can be implemented in practice, using state-of-the-art software components., This work has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”. L.E. Chatzieleftheriou is a Juan de la Cierva awardee (JDC2022-050266-I), funded by MCIU/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Nuberu : Reliable RAN Virtualization in Shared Platforms

  • García Avilés, Ginés
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Costa Pérez, Ana
  • Serrano Yáñez-Mingot, Pablo
  • Banchs Roca, Albert
RAN virtualization will become a key technology for the last mile of next-generation mobile networks driven by initiatives such as the O-RAN alliance. However, due to the computing fluctuations inherent to wireless dynamics and resource contention in shared computing infrastructure, the price to migrate from dedicated to shared platforms may be too high. Indeed, we show in this paper that the baseline architecture of a base station¿s distributed unit (DU) collapses upon moments of deficit in computing capacity. Recent solutions to accelerate some signal processing tasks certainly help but do not tackle the core problem: a DU pipeline that requires predictable computing to provide carrier-grade reliability. We present Nuberu, a novel pipeline architecture for 4G/5G DUs specifically engineered for non-deterministic computing platforms. Our design has one key objective to attain reliability: to guarantee a minimum set of signals that preserve synchronization between the DU and its users during computing capacity shortages and, provided this, maximize network throughput. To this end, we use techniques such as tight deadline control, jitter-absorbing buffers, predictive HARQ, and congestion control. Using an experimental prototype, we show that Nuberu attains 95% of the theoretical spectrum efficiency in hostile environments, where state-of-art approaches lose connectivity, and at least 80% resource savings, We would like to thank our shepherd and reviewers for their valuable comments and feedback. This work has been supported by the European Commission through Grant No. 101017109 (DAEMON project) and Grant No. 101015956 (Hexa-X project), and the CERCA Programme/Generalitat de Catalunya.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

CloudRIC: Open Radio Access Network (O-RAN) Virtualization with Shared Heterogeneous Computing

  • Lo Schiavo, Leonardo
  • García Avilés, Ginés
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Fiore, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
Proceedings of: MobiCom 2024. The 30th Annual International Conference on Mobile Computing and Networking. Nov. 18-22, 2024, Washington, D.C., USA, Open and virtualized Radio Access Networks (vRANs) are breeding a new market with unprecedented opportunities. However, carrier-grade vRANs today are expensive and energy-hungry, as they rely on hardware accelerators (HAs) that are dedicated to individual distributed units (DUs). In this paper, we argue that sharing pools of heterogeneous processors among DUs leads to more cost- and energy-efficient vRANs. We then design CloudRIC, a system that, powered by lightweight data-driven models, meets specific reliability targets while (i) coordinating access between DUs and heterogeneous computing infrastructure; and (ii) assisting DUs with compute-aware radio scheduling procedures. Experiments on a GPU-accelerated O-Cloud show that CloudRIC can achieve, respectively, 3x and 15x mean gains in energy- and cost-efficiency under real RAN workloads while ensuring 99.999% reliability even in dense scenarios., Work supported by the EC via grants no. 101017109 (DAEMON) and 101139270 (ORIGAMI), by NextGeneration EU through UNICO I+D grants no. TSI-063000-2021 (OPEN6G) and 022/0005395 (CLARION), and by CERCA Programme
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Bayesian online learning for energy-aware resource orchestration in virtualized RANs

  • Ayala Romero, José A.
  • García-Saavedra, Andrés
  • Costa-Pérez, Xavier
  • Iosifidis, George
Proceedings of: IEEE International Conference on Computer Communications, 10-13 May 2021, Vancouver, BC, Canada., Radio Access Network Virtualization (vRAN) will spearhead the quest towards supple radio stacks that adapt to heterogeneous infrastructure: from energy-constrained platforms deploying cells-on-wheels (e.g., drones) or battery-powered cells to green edge clouds. We perform an in-depth experimental analysis of the energy consumption of virtualized Base Stations (vBSs) and render two conclusions: (i) characterizing performance and power consumption is intricate as it depends on human behavior such as network load or user mobility; and (ii) there are many control policies and some of them have non-linear and monotonic relations with power and throughput. Driven by our experimental insights, we argue that machine learning holds the key for vBS control. We formulate two problems and two algorithms: (i) BP-vRAN, which uses Bayesian online learning to balance performance and energy consumption, and (ii) SBP-vRAN, which augments our Bayesian optimization approach with safe controls that maximize performance while respecting hard power constraints. We show that our approaches are data-efficient and have provably performance, which is paramount for carrier-grade vRANs. We demonstrate the convergence and flexibility of our approach and assess its performance using an experimental prototype., This work was supported by the European Commission through Grant No. 856709 (5Growth) and Grant No. 101017109 (DAEMON); and by SFI through Grant No. SFI 17/CDA/4760.
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Evaluating the Impact of Flow Length on the Performance of In-Switch Inference Solutions

  • Gucciardo, Michele|||0000-0001-5689-9949
  • Bütün, Beyza|||0000-0001-7442-9668
  • Akem, Aristide Tanyi-Jong
  • Fiore, Marco|||0000-0002-0772-9967
Workshop name: The 11th International Workshop on Computer and Networking Experimental Research using Testbeds (CNERT), As modern networks evolve into complex systems to support next-generation applications with strict latency requirements, in-switch machine learning (ML) has emerged as a candidate technology for minimizing ML inference latency. Multiple solutions, mostly based on Decision Tree (DT) and Random Forest (RF) models, have been proposed in that regard for inference at packet level (PL) or flow level (FL) or simultaneously at PL and FL. Such heterogeneity in the inference target leads to the use of varying performance metrics for evaluating the solutions, rendering a fair comparison between them difficult. In this paper, we perform a comprehensive evaluation of 5 leading solutions for DT/RF-based in-switch inference. We replicate and deploy the solutions into a real-world testbed with Intel Tofino switches, and run experiments with measurement data from 4 datasets. We then evaluate their performance using (i) the original metric used in the solution’s paper, and (ii) a novel FL metric which evaluates every solution at FL. This FL metric enables us to delve into an extensive analysis of how the solutions perform on flows of different lengths in diverse use cases. Results show that while some solutions perform similarly across use cases and flow sizes, others show inconsistent behaviours that we discuss., Spanish Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU through the UNICO 5G I+D project no.TSI-063000-2021-52 “AEON-ZERO", Spanish Ministry of Science and Innovation through grant no. PID2021-128250NB-I00 “bRAIN”, CHIST-ERA grant no. CHIST-ERA-20-SICT- 001 “ECOMOME”, via grant PCI2022-133013 of Agencia Estatal de Investigación, European Union’s Horizon Europe research and innovation programme under grant agreement no. 101017109 "DAEMON", TRUE, inpress
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

DAEMON: A Network Intelligence Plane for 6G Networks

  • Camelo, Miguel
  • Gramaglia, Marco
  • Soto, Paola
  • Fuentes, Lidia
  • Ballestreros, Joaquín
  • Bazco-Nogueras, Antonio|||0000-0001-7367-0898
  • García, Ginés
  • Latré, Steven
  • Garcia-Saavedra, Andres
  • Fiore, Marco|||0000-0002-0772-9967
While there is a clear trend towards network automation through the usage of Artificial Intelligence (AI) and Machine Learning (ML) solutions, the major reference network architectures are still not natively including all the mechanisms needed to handle Network Intelligence (NI). This paper introduces a novel architecture proposed within the EU-funded DAEMON project, which includes a Network Intelligence Plane (NIP) that natively integrates NI into the network operation, management, and orchestration procedures. We do so by analyzing the gaps in current reference architectures and designing a Network Intelligence Orchestration (NIO) that handles the most important NI-related mechanisms such as lifecycle management, coordination, and data management., European Commission, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Showcasing In-Switch Machine Learning Inference

  • Akem, Aristide Tanyi-Jong
  • Bütün, Beyza|||0000-0001-7442-9668
  • Gucciardo, Michele|||0000-0001-5689-9949
  • Fiore, Marco|||0000-0002-0772-9967
Recent endeavours have enabled the integration of trained machine learning models like Random Forests in resource-constrained programmable switches for line rate inference. In this work, we first show how packet-level information can be used to classify individual packets in production-level hardware with very low latency. We then demonstrate how the newly proposed Flowrest framework improves classification performance relative to the packet-level approach by exploiting flow-level statistics to instead classify traffic flows entirely within the switch without considerably increasing latency. We conduct experiments using measurement data in a real-world testbed with an Intel Tofino switch and shed light on how Flowrest achieves an F1-score of 99% in a service classification use case, outperforming its packet-level counterpart by 8%., European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”, CHIST-ERA grant no. CHIST-ERA-20-SICT- 001 “ECOMOME”, via grant PCI2022-133013 of Agencia Estatal de Investigación, Best Demo Award, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Network Intelligence in 6G: challenges and opportunities

  • Banchs, Albert|||0000-0003-3544-8537
  • Fiore, Marco|||0000-0002-0772-9967
  • Garcia-Saavedra, Andres
  • Gramaglia, Marco
The success of the upcoming 6G systems will largely depend on the quality of the Network Intelligence (NI) that will fully automate network management. Artificial Intelligence (AI) models are commonly regarded as the cornerstone for NI design, as they have proven extremely successful at solving hard problems that require inferring complex relationships from entangled, massive (network traffic) data. However, the common approach of plugging ‘vanilla’ AI models into controllers and orchestrators does not fulfil the potential of the technology. Instead, AI models should be tailored to the specific network level and respond to the specific needs of network functions, eventually coordinated by an end-to-end NI-native architecture for 6G. In this paper, we discuss these challenges and provide results for a candidate NI-driven functionality that is properly integrated into the proposed architecture: network capacity forecasting., European Union, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Flowrest: Practical Flow-Level Inference in Programmable Switches with Random Forests

  • Akem, Aristide Tanyi-Jong
  • Gucciardo, Michele|||0000-0001-5689-9949
  • Fiore, Marco|||0000-0002-0772-9967
User-plane machine learning facilitates low-latency, high-throughput inference at line rate. Yet, user planes are highly constrained environments, and restrictions are especially marked in programmable switches with limited memory and minimum support for mathematical operations or data types. Thus, current solutions for in-switch inference that are compatible with production-level hardware lack support for complex features or suffer from limited scalability, and hit performance barriers in complex tasks involving large decision spaces. To address this limitation, we present Flowrest, a first complete Random Forest (RF) model implementation that operates at the level of individual flows in commercial switches. Our solution builds on (i) an original framework to embed flow-level machine learning models into programmable switch ASICs, and (ii) novel guidelines for tailoring RF models to operations in programmable switches already at the design stage. We implement Flowrest as an open-source software using the P4 language, and assess its performance in an experimental platform based on Intel Tofino switches. Tests with tasks of unprecedented complexity show how our model can improve accuracy by up to 39% over previous approaches to implement RF models in real-world equipment., European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”, European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Henna: hierarchical machine learning inference in programmable switches

  • Akem, Aristide Tanyi-Jong
  • Bütün, Beyza|||0000-0001-7442-9668
  • Gucciardo, Michele|||0000-0001-5689-9949
  • Fiore, Marco|||0000-0002-0772-9967
The recent proliferation of programmable network equipment has opened up new possibilities for embedding intelligence into the data plane. Deploying models directly in the data plane promises to achieve high throughput and low latency inference capabilities that cannot be attained with traditional closed loops involving control-plane operations. Recent efforts have paved the way for the integration of trained machine learning models in resource-constrained programmable switches, yet current solutions have significant limitations that translate into performance barriers when coping with complex inference tasks. In this paper, we present Henna, a first in-switch implementation of a hierarchical classification system. The concept underpinning our solution is that of splitting a difficult classification task into easier cascaded decisions, which can then be addressed with separated and resource-efficient tree-based classifiers. We propose a design of Henna that aligns with the internal organization of the Protocol Independent Switch Architecture (PISA), and integrates state-of-the-art strategies for mapping decision trees to switch hardware. We then implement Henna into a real testbed with off-the-shelf Intel Tofino programmable switches using the P4 language. Experiments with a complex 21-category classification task based on measurement data demonstrate how Henna improves the F1 score of an advanced single-stage model by 21%, while keeping usage of switch resources at 8% on average., European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”, CHIST-ERA grant no. CHIST-ERA-20-SICT- 001 “ECOMOME”, via grant PCI2022-133013 of Agencia Estatal de Investigación, European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Implementation and Scalability Evaluation of Random Forests for In-Switch Inference

  • Akem, Aristide Tanyi-Jong
  • Gucciardo, Michele|||0000-0001-5689-9949
  • Fiore, Marco|||0000-0002-0772-9967
We comparatively evaluate state-of-the-art solutions for in-switch machine learning inference. We demonstrate that random forest (RF) models attain accuracies on par with those of approaches based on neural networks, which are also less amenable to in-switch operation. Next, we implement the top two solutions for in-switch random forest representation using a unified framework that we propose to ensure their fair comparison. We then verify their performance, resource consumption and scalability with respect to the capabilities of production-grade programmable switches., European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”, FALSE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Demonstrating Flow-Level In-Switch Inference

  • Gucciardo, Michele|||0000-0001-5689-9949
  • Akem, Aristide Tanyi-Jong
  • Bütün, Beyza|||0000-0001-7442-9668
  • Fiore, Marco|||0000-0002-0772-9967
Existing approaches for in-switch inference with Random Forest (RF) models that can run on production-level hardware do not support flow-level features and have limited scalability to the task size. This leads to performance barriers when tackling complex inference problems with sizable decision spaces. Flowrest is a complete RF model framework that fills existing gaps in the existing literature and enables practical flow-level inference in commercial programmable switches. In this demonstration, we exhibit how Flowrest can classify individual traffic flows at line rate in an experimental platform based on Intel Tofino switches. To this end, we run experiments with real-world measurement data, and show how Flowrest yields improvements in accuracy with respect to solutions that are limited to packet-level inference in programmable hardware., European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”, CHIST-ERA grant no. CHIST-ERA-20-SICT- 001 “ECOMOME”, via grant PCI2022-133013 of Agencia Estatal de Investigación, TRUE, pub
IMDEA Networks Institute Digital Repository
Publication Contribución de congreso (ConferenceOutput)

Orchestration Procedures for the Network Intelligence Stratum in 6G Networks

  • Chatzieleftheriou, Livia Elena|||0000-0002-8786-2337
  • Gramaglia, Marco
  • Camelo, Miguel
  • Garcia-Saavedra, Andres
  • Kosmatos, Evangelos
  • Gucciardo, Michele|||0000-0001-5689-9949
  • Soto, Paola
  • Iosifidis, George
  • Fuentes, Lidia
  • García, Ginés
  • Lutu, Andra
  • Baldoni, Gabriele
  • Fiore, Marco|||0000-0002-0772-9967
The quest for autonomous mobile networks introdu- ces the need for fully native support for Network Intelligence (NI) algorithms, typically based on Artificial Intelligence tools like Machine Learning, which shall be gathered into a NI stratum. The NI stratum is responsible for the full automation of the NI operation in the network, including the management of the life-cycle of NI algorithms, in a way that is synergic with traditional network management and orchestration framework. In this regard, the NI stratum must accommodate the unique requirements of NI algorithms, which differ from the ones of, e.g., virtual network functions, and thus plays a critical role in the native integration of NI into current network architectures. In this paper, we leverage the recently proposed concept of Network Intelligence Orchestrator (NIO) to (i) define the specific requirements of NI algorithms, and (ii) discuss the procedures that shall be supported by an NIO sitting in the NI stratum to effectively manage NI algorithms. We then (iii) introduce a reference implementation of the NIO defined above using cloud- native open-source tools., European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”, TRUE, pub